INDEX

Explanations

large numerical values

oai_token-act-pair · gpt-3.5-turbo

numeric expressions and quantities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sapp

-0.69

-0.67

atown

-0.67

£ı

-0.66

 compr

-0.64

helps

-0.63

Joined

-0.61

 Bounty

-0.60

lication

-0.60

Ran

-0.59

POSITIVE LOGITS

 billion

1.23

 trillion

1.22

billion

1.19

%-

1.04

 million

1.03

 decades

0.98

century

0.96

percent

0.94

 crore

0.93

million

0.93

Activations Density 0.216%

large numerical values

numeric expressions and quantities

No Comments

No Known Activations